INDEX

Explanations

language describing competitive match results

oai_token-act-pair · gemini-2.0-flash

non-standard or unusual words

np_token-act-pair-logits · gpt-4o-mini

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OGND

-0.82

tagHelperRunner

-0.75

uxxxx

-0.70

 disambiguazione

-0.65

mybatisplus

-0.63

IVEREF

-0.60

AsUp

-0.60

MethodManager

-0.59

 Komun

-0.59

HandlerContext

-0.59

POSITIVE LOGITS

sief

0.58

tenth

0.47

備

0.46

maq

0.45

 luar

0.45

Dup

0.44

xhr

0.43

resso

0.43

OptionsMenu

0.43

]<<"

0.43

Activations Density 0.398%

language describing competitive match results

non-standard or unusual words

No Comments

No Known Activations